{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SX2DONPT7BC4AVTZV7ZMOF6KU6","short_pith_number":"pith:SX2DONPT","canonical_record":{"source":{"id":"2607.27178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b4af44bcfa4d5be02956979d1516566d727856bdffdf1664ae70ae804595c293","abstract_canon_sha256":"a95705fd65be424beddc12666cb3ea1a705c2e56b1b9287572ca7143627e4569"},"schema_version":"1.0"},"canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","source":{"kind":"arxiv","id":"2607.27178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27178","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27178v1","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27178","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"SX2DONPT7BC4","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"SX2DONPT7BC4AVTZ","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"SX2DONPT","created_at":"2026-07-30T01:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SX2DONPT7BC4AVTZV7ZMOF6KU6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b4af44bcfa4d5be02956979d1516566d727856bdffdf1664ae70ae804595c293","abstract_canon_sha256":"a95705fd65be424beddc12666cb3ea1a705c2e56b1b9287572ca7143627e4569"},"schema_version":"1.0"},"canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","last_reissued_at":"2026-07-30T01:23:57.983325Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:57.983325Z"},"source_kind":"arxiv","source_id":"2607.27178","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1IGlwKErnSvhjsnD1KZeh/aKgL9PsTL3B5JtrJrLFO5xCHocCOo//BwVi2xv6Gl2b0CEGmrL0jZ0b0KIsVWbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:33:35.861030Z"},"content_sha256":"4c6ae2b13830c34b54c1adc108dabc228228ef40c8aae9f1510a7d4b353bb733","schema_version":"1.0","event_id":"sha256:4c6ae2b13830c34b54c1adc108dabc228228ef40c8aae9f1510a7d4b353bb733"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SX2DONPT7BC4AVTZV7ZMOF6KU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Am\\'elie Chatelain, Antoine Chaffin, Paulo Roberto Moura Junior, Rapha\\\"el Sourty","submitted_at":"2026-07-29T17:50:51Z","abstract_excerpt":"State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual retrieval through translate-train. We first reconstruct and curate 665M English contrastive pre-training pairs from 1.4B pairs across 34 public sources and build 1.88M supervised fine-tuning pairs with mined hard negatives. Training yields two 149M-parameter models: DenseOn, a single-vector dense model, and LateOn, a ColBERT-style late-interaction model. They ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27178","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.27178/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RKkqmbGUWnQlS2UCnofyvI+AlFAU+ZfV1E1/0+M9RTKgs+jLwI+DSH2irB/OTJJOP1WW008y2nFy643TszGcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:33:35.861941Z"},"content_sha256":"8e3a42f4800abc7c34465804a605c2b45f9a3cbf88b9483a69d48383b6adaba2","schema_version":"1.0","event_id":"sha256:8e3a42f4800abc7c34465804a605c2b45f9a3cbf88b9483a69d48383b6adaba2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/bundle.json","state_url":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T21:33:35Z","links":{"resolver":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6","bundle":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/bundle.json","state":"https://pith.science/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX2DONPT7BC4AVTZV7ZMOF6KU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SX2DONPT7BC4AVTZV7ZMOF6KU6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a95705fd65be424beddc12666cb3ea1a705c2e56b1b9287572ca7143627e4569","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","title_canon_sha256":"b4af44bcfa4d5be02956979d1516566d727856bdffdf1664ae70ae804595c293"},"schema_version":"1.0","source":{"id":"2607.27178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27178","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27178v1","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27178","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"SX2DONPT7BC4","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"SX2DONPT7BC4AVTZ","created_at":"2026-07-30T01:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"SX2DONPT","created_at":"2026-07-30T01:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:8e3a42f4800abc7c34465804a605c2b45f9a3cbf88b9483a69d48383b6adaba2","target":"graph","created_at":"2026-07-30T01:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.27178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual retrieval through translate-train. We first reconstruct and curate 665M English contrastive pre-training pairs from 1.4B pairs across 34 public sources and build 1.88M supervised fine-tuning pairs with mined hard negatives. Training yields two 149M-parameter models: DenseOn, a single-vector dense model, and LateOn, a ColBERT-style late-interaction model. They ac","authors_text":"Am\\'elie Chatelain, Antoine Chaffin, Paulo Roberto Moura Junior, Rapha\\\"el Sourty","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27178","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c6ae2b13830c34b54c1adc108dabc228228ef40c8aae9f1510a7d4b353bb733","target":"record","created_at":"2026-07-30T01:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a95705fd65be424beddc12666cb3ea1a705c2e56b1b9287572ca7143627e4569","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T17:50:51Z","title_canon_sha256":"b4af44bcfa4d5be02956979d1516566d727856bdffdf1664ae70ae804595c293"},"schema_version":"1.0","source":{"id":"2607.27178","kind":"arxiv","version":1}},"canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f43735f3f845c05679aff2c717caa7acdde3f4249249d0982c062a8ac70120","first_computed_at":"2026-07-30T01:23:57.983325Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:57.983325Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c6ae2b13830c34b54c1adc108dabc228228ef40c8aae9f1510a7d4b353bb733","sha256:8e3a42f4800abc7c34465804a605c2b45f9a3cbf88b9483a69d48383b6adaba2"],"state_sha256":"9206a90474d0d9594c03a8acdf527dd625c93a30c159f0c83d252e3070a3ed46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mndNntJp8lIey+lvxo1HECcE+lvE38i7UWapPQXR1V1YdCEwxW6v5HYmYTvXq16kFSw/DMBrB/gGfTqvc/amDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:33:35.867008Z","bundle_sha256":"2b80d962efd03a980838ec402af664949c7ad96ac590caa45adb4acfcc479ba7"}}